Multitask Parsing Across Semantic Representations
This work addresses the problem of enhancing semantic parsing for NLP researchers and practitioners, but it is incremental as it applies an existing multitask learning method to a specific parsing task.
The paper tackled the challenge of improving semantic parsing performance by using multitask learning with auxiliary tasks like AMR, SDP, and UD parsing, and showed that this approach significantly improved UCCA parsing in both in-domain and out-of-domain settings.
The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.